Nagish captions calls faster than other providers in FCC tests

In the FCC's National Test Lab, Nagish's automatic captions had a median delay of 1.0 seconds, against 1.8-2.4 seconds for other providers, with comparable word error rates.

  • Not rated a person

    The FCC measured delay and accuracy on test calls and later found that both services met its minimum standards, but it reports no outcome for users.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Three independent regulatory documents support the benefit.

Compared with

Aggregate average caption delay of other IP CTS providers in the same two call scenarios. Measured.

Without the system
1.8-2.4 seconds
With it
1.0 seconds
The system’s part
The National Test Lab measured Nagish's automatic captions against other providers' aggregated results on the same call scenarios, which isolates the recognizer's output. The FCC does not say which captioning mode produced the other providers' results. Its finding on text-to-speech rests on tests by Cositics, LLC, which Nagish filed. A competitor's comments refer to Nagish's use of artificial intelligence, but the FCC does not show that the recognizers learn from data.
Later
Persisted, 9 June 2026. The FCC granted Nagish five-year full certification for fully automated captions and relay, after reviewing its application, amendments and annual reports.
Not yet checked
LimitsCosts and harmsLearns from data

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
Nagish fully automatic IP CTS (automatic speech recognition) and IP Relay (speech recognition with text-to-speech), delivered by smartphone app
Made by
Nagish, Inc., on speech recognition and text-to-speech from unnamed vendors
Used by
Nagish, Inc.
Where
United States
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Documenting/Recording Information, Interpreting the Meaning of Information for Others
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    Federal Communications Commission, Consumer and Governmental Affairs Bureau. Order, DA 24-12, CG Docket No. 03-123 (conditional certification of Nagish, Inc. to provide IP CTS on a fully automatic basis). Adopted and released 4 January 2024.

    In performance testing by the Commission’s National Test Lab (NTL), Nagish’s median caption delay for two call scenarios was 1.0 seconds, compared to an aggregate average of 1.8-2.4 seconds for other IP CTS providers.
    In testing by NTL, Nagish’s Word Error Rate for three call scenarios ranged from 2.1% to 9.6%, comparable to other IP CTS providers’ aggregated Word Error Rate results, which averaged from 2.0% to 7.4% in the same call scenarios.

  2. Regulatory document, by authors with no tie to the system.

    Federal Communications Commission, Consumer and Governmental Affairs Bureau. Order, DA 24-1292, CG Docket No. 03-123 (conditional certification of Nagish, Inc. to provide fully automatic Internet Protocol Relay Service). Adopted and released 23 December 2024.

    With respect to this particular application, test results for Nagish’s ASR support the likelihood that its IP Relay service will achieve a high level of accuracy in the conversion of speech to text.
    These test results sufficiently confirm that Nagish’s fully automatic IP Relay service will accurately, clearly, and articulately convert a user’s text to speech.

  3. Regulatory document, by authors with no tie to the system.

    Federal Communications Commission, Consumer and Governmental Affairs Bureau. Public Notice, DA 26-566, CG Docket No. 03-123: Grant of Certification for Nagish, Inc., to Provide Internet Protocol Captioned Telephone Service and Internet Protocol Relay Service. Released 9 June 2026.

    This grant of full certification authorizes Nagish to offer fully automated IP CTS using automatic speech recognition (ASR) and fully automated IP Relay using ASR and text-to-speech (TTS) technology to all eligible consumers.

Details

AI system

Workflow

Nagish contracted with several speech recognition vendors and tested each under an array of call conditions. The services ran as an app on users' own Android or iOS phones. The relay voiced users' typed text with text-to-speech and transcribed the other party with the same recognizer as the captions.

Follow-up

Conditions for replication

The services must meet the FCC's minimum standards in actual operation. Nagish may not keep call transcripts after a call ends. Billing must match each user's registration for captions, relay or both.

Entry details

Sector

Telecommunications relay services / accessibility for people who are deaf, hard of hearing or speech disabled.

Purpose

Nagish built its app to let people with hearing loss or speech disabilities make phone calls with automatic captions or typed text, without a communications assistant.

30 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Nagish captions calls faster than other providers in FCC tests (AIBD-0997). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-0997.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions